Public GPU and NPU uploads

AMD RX 9060 XT 16 GB

2048 Stream Processors

Type

GPU

VRAM

16 GB

Memory bandwidth

320 GB/s

TDP

160 W

Benchmark results

LLM name	Quantization	Used tokens ↓ Token	Prompt processing Token/s	TTFT ms	Token Generation Token/s	Backend	Engine	Power W	Latest upload	User
Llama 2 7B	Q4_0	512	2,141.67	239.00 ms	71	llama.cpp	Vulkan	—	uploaded 4 weeks ago	AI Hardware Research System
Standardized test Llama-Bench Used prompt llama-bench -p 512 -n 128 Notes llama-bench / Vulkan scoreboard; Flash Attention deaktiviert Evidence Source llama.cpp Vulkan scoreboard github.com
Llama 2 7B	Q4_0	512	2,141.67	239.00 ms	71	llama.cpp	Vulkan	—	uploaded 4 weeks ago	AI Hardware Research System
Standardized test Llama-Bench Used prompt llama-bench -p 512 -n 128 Notes llama-bench / Vulkan scoreboard; Flash Attention deaktiviert; Hinweis: Im Thread gibt es auch einen weiteren Run mit 1915.41 / 70.52. Evidence Source llama.cpp Vulkan scoreboard github.com